flammen15-gutenberg-DPO-v1-7B: benchmark results
A DPO fine-tune released by flammen.ai of nbeerbower/flammen15-mistral-7B, using jondurbin/gutenberg-dpo-v0.1. Provider: flammen.ai. Access: Open.
Aggregate Rating 1453 ± 34, rank #3630 of 10916 rated models, from 12 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard v1 - GSM8K | 71.34 | Accuracy (%) (5-shot) | 95.7 |
| Open LLM Leaderboard v1 - TruthfulQA MC2 | 71.98 | MC2 (%) (0-shot) | 92.9 |
| Open LLM Leaderboard v1 - HellaSwag | 88.37 | Normalized accuracy (%) (10-shot) | 91.3 |
| Open LLM Leaderboard v1 - ARC Challenge | 71.5 | Normalized accuracy (%) (25-shot) | 89.4 |
| Open LLM Leaderboard v1 - WinoGrande | 82.56 | Accuracy (%) (5-shot) | 84.6 |
| Open LLM Leaderboard v1 - MMLU | 64.87 | Accuracy (%) (5-shot) | 77.7 |
| Open LLM Leaderboard - MuSR | 42.93 | Score | 70 |
| Open LLM Leaderboard - BBH | 52.03 | Score | 59.2 |
| Open LLM Leaderboard - IFEval | 47.98 | Score | 55.8 |
| Open LLM Leaderboard - MMLU-Pro | 31.86 | Score | 43.4 |
| Open LLM Leaderboard - MATH Level 5 | 7.63 | Score | 39.6 |
| Open LLM Leaderboard - GPQA | 28.44 | Score | 39.4 |
Interactive version: theaggregate.ai/model?slug=flammen15-gutenberg-dpo-v1-7b · How It Works · Data refreshed daily, snapshot 2026-11-08.